Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5826 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.7143. Min Act: -0.1700
Data Index: 501717 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.5268. Min Act: -0.1700
Data Index: 1180652 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.5268. Min Act: -0.1700
Data Index: 6262124 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.4643. Min Act: -0.1700
Data Index: 920538 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.4643. Min Act: -0.1700
Data Index: 4777068 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.4643. Min Act: -0.1700
Data Index: 8083456 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.4018. Min Act: -0.1700
Data Index: 6525160 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.4018. Min Act: -0.1700
Data Index: 8264982 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.2768. Min Act: -0.1700
Data Index: 920535 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.2143. Min Act: -0.1700
Data Index: 920536 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.0893. Min Act: -0.1700
Data Index: 1572811 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.0268. Min Act: -0.1700
Data Index: 849843 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.0268. Min Act: -0.1700
Data Index: 7772363 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.0268. Min Act: -0.1700
Data Index: 3104046 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.0268. Min Act: -0.1700
Data Index: 2786297 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7143. Min Range: -9.7143
Max Act: 9.0893. Min Act: -0.1700
Data Index: 7179585 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7143. Min Range: -9.7143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 824160 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7143. Min Range: -9.7143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 2786301 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7143. Min Range: -9.7143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 1695979 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7143. Min Range: -9.7143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 6367038 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19